• Journal of Intelligence and Information Systems
• /
• v.17 no.3
• /
• pp.25-41
• /
• 2011

Recently, support vector machines (SVMs) are being recognized as competitive tools as compared with other data mining techniques for solving pattern recognition or classification decision problems. Furthermore, many researches, in particular, have proved them more powerful than traditional artificial neural networks (ANNs) (Amendolia et al., 2003; Huang et al., 2004, Huang et al., 2005; Tay and Cao, 2001; Min and Lee, 2005; Shin et al., 2005; Kim, 2003).The classification decision, such as a binary or multi-class decision problem, used by any classifier, i.e. data mining techniques is so cost-sensitive particularly in financial classification problems such as the credit ratings that if the credit ratings are misclassified, a terrible economic loss for investors or financial decision makers may happen. Therefore, it is necessary to convert the outputs of the classifier into wellcalibrated posterior probabilities-based multiclass credit ratings according to the bankruptcy probabilities. However, SVMs basically do not provide such probabilities. So it required to use any method to create the probabilities (Platt, 1999; Drish, 2001). This paper applied AdaBoost algorithm-based support vector machines (SVMs) into a bankruptcy prediction as a binary classification problem for the IT companies in Korea and then performed the multi-class credit ratings of the companies by making a normal distribution shape of posterior bankruptcy probabilities from the loss functions extracted from the SVMs. Our proposed approach also showed that their methods can minimize the misclassification problems by adjusting the credit grade interval ranges on condition that each credit grade for credit loan borrowers has its own credit risk, i.e. bankruptcy probability.

• Progress in Medical Physics
• /
• v.22 no.4
• /
• pp.178-183
• /
• 2011

The applicability and feasibility of TomoTherapy in the lung radiation surgery was analyzed by comparison of the calculated dose distribution in TomoTherapy planning with the results of conventional IMRS (intensity modulated radiation surgery) using LINAC (linear accelerator). The acquired CT (computed tomograph) images of total 10 patients whose tumors' motion were less than 5 mm were used in the radiation surgery planning and the same prescribed dose and the same dose constraints were used between TomoTherapy and LINAC. The results of TomoTherapy planning fulfilled the dose requirement in GTV (gross tumor volume) and OAR (organ at risk) in the same with the conventional IMRS using LINAC. TomoTherapy was superior in the view point of low dose in the normal lung tissue and conventional LINAC was superior in the dose homogeneity in GTV. The calculated time for treatment beam delivery was long more than two times in TomoTherapy compared with the conventional LINAC. Based on the results in this study, TomoTherapy can be evaluated as an effective way of lung radiation surgery for the patients whose tumor motion is little when the optimal planning is produced considering patient's condition and suitability of dose distribution.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.5
• /
• pp.389-397
• /
• 1998

For an effective and efficient management of large amounts of preservice/inservice inspection(PSI/ISI) data in nuclear power plants, an intellegent Windows 95-based data management program was developed. This program enables the prompt extraction of previously conducted PSI/ISI conditions and results so that the time-consuming data management, painstaking data processing and analysis in the past are avoided. The program extracts, and the associated remedies. Furthermore, additional inspection data and comments can be easily added or deleted for subsequent PSI/ISI operation. Although the initial version of the program was applied to Kori nuclear power plant, this program can be equally applied to other nuclear power plant. And also this program can be used to offer the fundamental data for application of evaluation data related to fracture mechanics analysis(FMA), probabilistic reliability assessment(PRA) of PSI/ISI results, performance demonstration initiative(PDI) and risk-informed ISI based on probability of detection(POD) information of ultrasonic examination. Besides, the program can be further developed as a unique PSI/ISI data management expert system that can be apart of PSI/ISI data management expert system that can be a part of PSI/ISI Total Support System(TSS) for Korean nuclear power plants.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.6
• /
• pp.3779-3784
• /
• 2013

Aims: To determine the clinical, pathological and prognostic features associated with triple-negative breast cancer (TNBC). Methods: Clinical and histologic data of 21,749 breast cancer patients who were treated at Tianjin Medical University Cancer Institute and Hospital between July 2002 and December 2011 were collected. Patients were divided into two groups: those with TNBC and those with other types of breast cancer. Patients and tumor characteristics were compared between the two groups using the Chi-square test. The prognostic results of 9,823 patients in the study population were also analyzed to determine long-term survival rates in the two groups of breast cancer patients. Results: Among the breast cancer patients treated in our hospital between 2003 and 2011, 10.4%-13.5% of them had triple-negative breast cancers. Data analyses revealed significant differences in disease onset age, family history of breast cancer, tumor size, tumor histologic grade, lymph note positivity and metastatic status between TNBC and non-TNBC patients. There were also significant differences in 5-year, 7-year and 9-year disease-free and 7-year and 9-year overall survival probability between the groups. Conclusions:TNBC are associated with younger disease onset age, larger tumor size, higher rate of axillary lymph node positivity, and higher tumor histologic grade. TNBC is also related to family history of breast cancer, increased metastatic risk and poor prognosis.

• Journal of Korean Neurosurgical Society
• /
• v.61 no.2
• /
• pp.127-166
• /
• 2018

Despite advancements in treating ruptured cerebral aneurysms, an aneurysmal subarachnoid hemorrhage (aSAH) is still a grave cerebrovascular disease associated with a high rate of morbidity and mortality. Based on the literature published to date, world-wide academic and governmental committees have developed clinical practice guidelines (CPGs) to propose standards for disease management in order to achieve the best treatment outcomes for aSAHs. In 2013, the Korean Society of Cerebrovascular Surgeons issued a Korean version of the CPGs for aSAHs. The group researched all articles and major foreign CPGs published in English until December 2015 using several search engines. Based on these articles, levels of evidence and grades of recommendations were determined by our society as well as by other related Quality Control Committees from neurointervention, neurology and rehabilitation medicine. The Korean version of the CPGs for aSAHs includes risk factors, diagnosis, initial management, medical and surgical management to prevent rebleeding, management of delayed cerebral ischemia and vasospasm, treatment of hydrocephalus, treatment of medical complications and early rehabilitation. The CPGs are not the absolute standard but are the present reference as the evidence is still incomplete, each environment of clinical practice is different, and there is a high probability of variation in the current recommendations. The CPGs will be useful in the fields of clinical practice and research.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.13 no.1
• /
• pp.101-113
• /
• 2010

Recently actual rainfall pattern is decreasing rainy days and increasing in rainfall intensity and the frequency of flood occurrence is also increased. To consider recent situation, Engineers use deterministic methods like a PMP(Probable Maximum Precipitation). If design storm wouldn't occur, increasing of design criteria is extravagant. In addition, the biggest structure cause trouble with residents and environmental problem. And then it is necessary to study considering probability of rainfall parameter in each sub-basin for design of water structure. In this study, stochastic rainfall patterns are generated by using log-ratio method, Johnson system and multivariate Monte Carlo simulation. Using the stochastic rainfall patterns, hydrological analysis, hydraulic analysis and 2nd flooding analysis were performed based on GIS for their applicability. The results of simulations are similar to the actual damage area so the methodology of this study should be used about making a flood risk map or regidental shunting rout map against the region.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.37 no.2
• /
• pp.207-212
• /
• 2010

Protein C deficiency increases the risk of thrombosis due to the lack of anticoagulant factor protein C. Among the numerous congenital protein C deficiencies, homozygous protein C deficiency has an especially low protein C activity level, that it is almost undetectable. It is a rare disease with a probability of 1:250000~500000. The signs and symptoms of homozygous protein C deficiency include purpuric, necrotic dermatosis, ecchymosis, blindness, and thrombosis in central nervous system. A 4-year-old girl was brought to the clinic with a chief complaint of extensive caries. The child was under warfarin medication in order to prevent possible complications during dental treatment. We consulted the pediatric department. Without warfarin intake, serious complications may occur due to thrombosis during dental treatment. Therefore, certain warfarin dosage (INR 3~5) and fresh frozen plasma as a backup for excessive hemorrhage were recommended. This child was a severely disabled child with the loss of vision, and it was difficult to manage her behavior effectively. Thus, dental treatment was carried out under general anesthesia, where bleeding control would be also easier to achieve.This report presents the case of a 4-year-old girl with protein C deficiency, who has received dental treatment for extensive caries under general anesthesia.

• Journal of Korea Water Resources Association
• /
• v.45 no.5
• /
• pp.505-516
• /
• 2012

The study applies a hydrologic simulation model, HEC-1 developed by Hydrologic Engineering Center to Daecheong dam watershed for modeling hourly inflows of Daecheong dam. Although the HEC-1 model provides an automatic optimization technique for some of the parameters, the built-in optimization model is not sufficient in estimating reliable parameters. In particular, the optimization model often fails to estimate the parameters when a large number of parameters exist. In this regard, a main objective of this study is to develop Bayesian Markov Chain Monte Carlo simulation based HEC-1 model (BHEC-1). The Clark IUH method for transformation of precipitation excess to runoff and the soil conservation service runoff curve method for abstractions were used in Bayesian Monte Carlo simulation. Simulations of runoff at the Daecheong station in the HEC-1 model under Bayesian optimization scheme allow the posterior probability distributions of the hydrograph thus providing uncertainties in rainfall-runoff process. The proposed model showed a powerful performance in terms of estimating model parameters and deriving full uncertainties so that the model can be applied to various hydrologic problems such as frequency curve derivation, dam risk analysis and climate change study.

• Korean Journal of Soil Science and Fertilizer
• /
• v.45 no.6
• /
• pp.1153-1156
• /
• 2012

Daegwallyeong area to be formed along the mountainous terrain more above 800 m of sea level is known as the cold zone to occur frequently wind, rain and fog. This study to evaluate the stability of crop production and agricultural production potential in the Daegwallyeong was calculated for the low temperature frequency of occurrence and potential evapotranspiration changes with announce the release of Korea Meteorological Administration (KMA) from 1972 to 2009 up to 38 years. Evapotranspiration calculated FAO and other international standard method authorized under the PENMAN-MONTEITH Method was used, and the low temperature onset and frequency of the Gumbel probability density function was used. As a result, the variation of day evaporation for 38 years were showed to respectively width of variation from maximum $9mm\;day^{-1}$ to minimum $0.5mm\;day^{-1}$. The frequency of reappearance to first emergence day that lasts more than 5 days with temperature $5^{\circ}C$ over is 3 April a 50-year frequency, 10 April a 25-year frequency, 20 April a 10-year frequency, 28 April a 5-year frequency, 8 May a 2-year frequency. Psychrotrophic crop to growth temperature more than $5^{\circ}C$ can be secured to stable production with planting after May 8, prior to planting for normal growth can be seen that the risk of growth.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.8
• /
• pp.86-93
• /
• 2018

This study examines the differences in the determinants of dividend payout across advance disclosure firms and ordinary disclosure firms using firm-level data from firms listed on the Korea Exchange. Results are as follows: First, firm characteristics of advance disclosure firms significantly differ from those of ordinary disclosure firms in all variables except sales growth and operating risk variables. Second, regression results show that the determinants of dividend payout from ordinary disclosure firms are generally similar to results of previous studies. However, determinants of advance disclosure firms contain only few variables such as Tobin's Q, corporate bond yield, and operating cash flows from conventional factors. Third, logistic regression results show that factors affecting the probability of dividend payment substantially differ across advance disclosure firms and ordinary disclosure firms. These results suggest that the motivation and incentive of dividend payout from firms choosing advance disclosure are substantially and systematically different from those of ordinary disclosure firms.